DIKUL - logo
E-resources
Full text
Peer reviewed Open access
  • Deep learning for 3D vision
    Guo, Yulan; Wang, Hanyun; Clark, Ronald; Berretti, Stefano; Bennamoun, Mohammed

    IET computer vision, October 2022, 2022-10-00, 20221001, 2022-10-01, Volume: 16, Issue: 7
    Journal Article

    With the rapid development of 3D imaging sensors, such as depth cameras and laser scanning systems, 3D data has become increasingly accessible. To evaluate the performance of proposed DEMVSNet, a noisy Technical University of Denmark dataset is generated by adding Gaussian-Poisson noise to each image, and the experimental results demonstrate the superiority of DEMVSNet on both the denoising and multi-view stereo reconstruction tasks. ...multi-scale features are extracted at three different scales and 6D pose is estimated through a dense regression module.